Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by kujenga • Search & Retrieval
An open-source MCP server that exposes a Zotero library to AI assistants, enabling search, metadata retrieval, and full-text access.
Search a user's Zotero library by text query and discover relevant items to cite or summarize.
Retrieve complete, structured metadata (authors, title, DOI, attachments) for a specific Zotero item to support citations or knowledge grounding.
Fetch full-text content (PDF text) from Zotero items to extract passages, answer questions, or perform deeper document analysis.
This project implements the Model Context Protocol (MCP) for Zotero, providing tools to search items, fetch detailed item metadata, and retrieve full text (e.g., PDF contents). It supports both the Zotero local API (when the desktop app is running) and the Zotero Web API (using an API key and library ID). The server can be run locally via uvx/pipx or in Docker, and is designed so MCP clients and agents can discover and call its tools to integrate Zotero libraries into assistant workflows. Note: full-text access via the local API may require a Zotero Beta build per the README.
Get metadata information about a specific Zotero item, given the item key.
Get the full text content of a Zotero item, given the item key of a parent item or specific attachment.
Search for items in your Zotero library, given a query string, query mode (titleCreatorYear or everything), and optional tag search (supports boolean searches). Returned results can be looked up with zotero_item_fulltext or zotero_item_metadata.
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.